大模型推理能力 - arXivDaily 专题

1904.02390 2019-04-05 cs.RO cs.AI cs.LG 62%

Interaction-aware Multi-agent Tracking and Probabilistic Behavior Prediction via Adversarial Learning

Jiachen Li, Hengbo Ma, Masayoshi Tomizuka

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments Accepted by 2019 International Conference on Robotics and Automation (ICRA)

1711.06006 2019-02-21 cs.LG cs.AI cs.NE cs.RO 62%

Hindsight policy gradients

Paulo Rauber, Avinash Ummadisingu, Filipe Mutz, Juergen Schmidhuber

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments Accepted to ICLR 2019

1812.02690 2019-01-29 cs.LG cs.AI stat.ML 62%

Provably Efficient Maximum Entropy Exploration

Elad Hazan, Sham M. Kakade, Karan Singh, Abby Van Soest

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments Updated experiment results; minor revisions in writing

1811.01848 2019-01-29 cs.LG cs.AI cs.RO stat.ML 62%

Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control

Kendall Lowrey, Aravind Rajeswaran, Sham Kakade, Emanuel Todorov, Igor Mordatch

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments The first two authors contributed equally. Accepted at ICLR 2019. Supplementary videos available at: https://sites.google.com/view/polo-mpc

1607.08289 2019-01-23 cs.AI cs.CY cs.HC cs.LG cs.RO 62%

Mammalian Value Systems

Gopal P. Sarma, Nick J. Hay

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments 12 pages

Journal ref Informatica Vol. 41 No. 3 (2017)

1901.00569 2019-01-04 cs.LG cs.AI stat.ML 62%

Human-Like Autonomous Car-Following Model with Deep Reinforcement Learning

Meixin Zhu, Xuesong Wang, Yinhai Wang

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Journal ref Transportation Research Part C: Emerging Technologies 2018

1811.11597 2018-11-29 cs.LG cs.AI stat.ML 62%

Automated Algorithm Selection: Survey and Perspectives

Pascal Kerschke, Holger H. Hoos, Frank Neumann, Heike Trautmann

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments This is the author's final version, and the article has been accepted for publication in Evolutionary Computation

1809.04506 2018-11-20 cs.LG cs.AI stat.ML 62%

Combined Reinforcement Learning via Abstract Representations

Vincent François-Lavet, Yoshua Bengio, Doina Precup, Joelle Pineau

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments Accepted to the Thirty-Third AAAI Conference On Artificial Intelligence, 2019

1806.01261 2018-10-18 cs.LG cs.AI stat.ML 62%

Relational inductive biases, deep learning, and graph networks

Peter W. Battaglia, Jessica B. Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez, Vinicius Zambaldi, Mateusz Malinowski, Andrea Tacchetti, David Raposo, Adam Santoro, Ryan Faulkner, Caglar Gulcehre, Francis Song, Andrew Ballard, Justin Gilmer, George Dahl, Ashish Vaswani, Kelsey Allen, Charles Nash, Victoria Langston, Chris Dyer, Nicolas Heess, Daan Wierstra, Pushmeet Kohli, Matt Botvinick, Oriol Vinyals, Yujia Li, Razvan Pascanu

专题命中规划推理：reasoning(abstract)；分类 cs.AI、cs.LG

1810.00510 2018-10-02 cs.AI cs.LG cs.MA stat.ML 62%

Interactive Agent Modeling by Learning to Probe

Tianmin Shu, Caiming Xiong, Ying Nian Wu, Song-Chun Zhu

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments 14 pages

1808.05032 2018-08-16 cs.AI cs.LG 62%

Deep RTS: A Game Environment for Deep Reinforcement Learning in Real-Time Strategy Games

Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments Proceedings of the IEEE International Conference on Computational Intelligence and Games (CIG 2018)

1709.07615 2018-07-10 cs.AI cs.LG 62%

Neural Networks for Predicting Algorithm Runtime Distributions

Katharina Eggensperger, Marius Lindauer, Frank Hutter

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Journal ref International Joint Conference on Artificial Intelligence (2018), 1442--1448

1804.06459 2018-06-25 cs.AI cs.LG stat.ML 62%

On Learning Intrinsic Rewards for Policy Gradient Methods

Zeyu Zheng, Junhyuk Oh, Satinder Singh

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

1806.02448 2018-06-08 cs.LG cs.AI cs.NE stat.ML 62%

Deep Reinforcement Learning for General Video Game AI

Ruben Rodriguez Torrado, Philip Bontrager, Julian Togelius, Jialin Liu, Diego Perez-Liebana

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments 8 pages, 4 figures, Accepted at the conference on Computational Intelligence and Games 2018 IEEE

1805.07708 2018-05-22 cs.LG cs.AI stat.ML 62%

A Lyapunov-based Approach to Safe Reinforcement Learning

Yinlam Chow, Ofir Nachum, Edgar Duenez-Guzman, Mohammad Ghavamzadeh

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

1704.00756 2017-11-16 cs.LG cs.AI stat.ML 62%

Multi-Advisor Reinforcement Learning

Romain Laroche, Mehdi Fatemi, Joshua Romoff, Harm van Seijen

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments Submitted at ICLR2018

1612.06018 2017-07-28 cs.LG cs.AI 62%

Self-Correcting Models for Model-Based Reinforcement Learning

Erik Talvitie

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments Original paper appeared in Proceedings of the 31st AAAI Conference on Artificial Intelligence, 2017. This version incorporates the appendix into document (rather than as supplementary material), corrects a minor error in Lemma 1, and fixes some type-os

Journal ref Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 2597-2603 (2017)

1610.03295 2016-10-12 cs.AI cs.LG stat.ML 62%

Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving

Shai Shalev-Shwartz, Shaked Shammah, Amnon Shashua

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

1605.08478 2016-06-17 cs.LG cs.AI 62%

Model-Free Imitation Learning with Policy Optimization

Jonathan Ho, Jayesh K. Gupta, Stefano Ermon

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments In Proceedings of the 33rd International Conference on Machine Learning, 2016

Journal ref JMLR W&CP 48 (2016) 2760-2769

1301.6690 2013-01-30 cs.AI cs.LG 62%

Model-Based Bayesian Exploration

Richard Dearden, Nir Friedman, David Andre

专题命中规划推理：reasoning(abstract)；分类 cs.AI、cs.LG

Comments Appears in Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence (UAI1999)

1210.4889 2012-10-19 cs.LG cs.AI stat.ML 62%

Learning STRIPS Operators from Noisy and Incomplete Observations

Kira Mourao, Luke S. Zettlemoyer, Ronald P. A. Petrick, Mark Steedman

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments Appears in Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence (UAI2012)

1203.3518 2012-03-19 cs.LG cs.AI stat.ML 62%

Variance-Based Rewards for Approximate Bayesian Reinforcement Learning

Jonathan Sorg, Satinder Singh, Richard L. Lewis

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments Appears in Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence (UAI2010)

1111.3735 2011-11-17 cs.LG cs.AI 62%

A Bayesian Model for Plan Recognition in RTS Games applied to StarCraft

Gabriel Synnaeve, Pierre Bessière

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

Comments 7 pages; Artificial Intelligence and Interactive Digital Entertainment Conference (AIIDE 2011), Palo Alto : États-Unis (2011)

cs/0302015 2009-11-30 cs.AI cs.LG 62%

Unsupervised Learning in a Framework of Information Compression by Multiple Alignment, Unification and Search

J. G. Wolff

专题命中规划推理：reasoning(abstract)；分类 cs.AI、cs.LG

Comments 39 pages, 1 JPEG figure

2608.20830 2026-08-24 cs.CY cs.LG 新提交 61%

Fine-tuning LLMs for Tourist Trajectory Prediction using Field Experiment Data

利用实地实验数据微调大型语言模型（LLMs）进行游客轨迹预测

Tatsuya Amano, Hirozumi Yamaguchi

专题命中规划推理：reasoning(abstract)；分类 cs.LG；planning(comments)

AI总结该研究利用日本和歌山城公园的566条轨迹微调Llama-3.1-8B，实现49.1%的下一个兴趣点准确率，在样本不足场景泛化性强，为旅游轨迹预测提供了高保真行为模型及反事实分析基础。

Comments 5 pages, 4 figures. Accepted at the 2nd Workshop on AI for Urban Planning (AI4UP) at AAAI-26, Singapore, January 2026

2607.05888 2026-07-08 cs.CR cs.AI 新提交 61%

i-EXAM: Instructable and Explainable Attack Connectivity Graph Modeler

i-EXAM：可指导且可解释的攻击连通性图建模器

Rakesh Podder, Wadia Ganim, Sarath Sreedharan, Indrajit Ray, Indrakshi Ray

机构 * Colorado State University（科罗拉多州立大学）

专题命中规划推理：planning(abstract,comments)；分类 cs.AI

AI总结 i-EXAM工具借助规划编译，帮系统管理员创建复杂网络安全配置文件并做假设分析，可识别攻击路径、评估指标、生成强化策略，还能用大语言模型解释策略。

Comments In the Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS 2026)

2606.24669 2026-06-24 cs.AI 新提交 61%

LaGO: Latent Action Guidance for Online Reinforcement Learning

LaGO：面向在线强化学习的潜在动作引导

Kuan-Yen Liu, Ren-Jyun Huang, Ti-Rong Wu

机构 * Siebel School of Computing（计算科学系）； Data Science, University of Illinois Urbana-Champaign, USA（数据科学，伊利诺伊大学厄巴纳-香槟分校，美国）； Department of Computer Science, National Yang Ming Chiao Tung University, Taiwan（计算机科学系，National Yang Ming Chiao Tung大学，台湾）； Institute of Information Science, Academia Sinica, Taiwan（信息科学研究所， Academia Sinica，台湾）

专题命中规划推理：planning(abstract,comments)；分类 cs.AI

AI总结提出LaGO框架，利用预训练大语言模型作为潜在动作先验，软引导在线策略优化，在离散和连续控制基准上显著提升奖励与成功率。

Comments 9 pages, 2 figures. Accepted at the ICML 2026 Workshop on Large Language Models for Planning (LM4Plan)

2606.00104 2026-06-02 cs.RO cs.AI 61%

PEACE: A Planner-Executor Agent with Constraint Enforcement for UAVs

PEACE: 一种用于无人机的带约束执行的规划-执行智能体

Erdem Uysal, Timo Kehrer, Sebastiano Panichella

机构 * Institute of Computer Science, University of Bern（伯尔尼大学计算机科学研究所）； AI4I - The Italian Institute of Artificial Intelligence（意大利人工智能研究所）

专题命中规划推理：planning(abstract)；分类 cs.AI；reasoning(comments)

AI总结提出一种基于大语言模型的规划-执行智能体架构，通过解耦高层任务规划与低层控制，并引入约束执行层和有限重规划，实现无人机可解释、可约束的自主飞行。

Comments Accepted to ICRA 2026 Workshop on Semantics for Reliable Robot Autonomy: From Environment Understanding and Reasoning to Safe Interaction

2604.19043 2026-05-08 cs.AI 61%

Learning Lifted Action Models from Unsupervised Visual Traces

从无监督视觉轨迹中学习提升的动作模型

Kai Xi, Stephen Gould, Sylvie Thiébaux

机构 * School of Computing, The Australian National University（澳大利亚国立大学计算机学院）

专题命中规划推理：planning(abstract,comments)；分类 cs.AI

AI总结本文提出一种深度学习框架，通过无监督视觉轨迹学习状态预测、动作预测及提升的动作模型，并引入混合整数线性规划防止预测崩溃，提升模型在多领域中的全局一致性。

Comments Accepted to the 36th International Conference on Automated Planning and Scheduling (ICAPS-26)

2405.10729 2026-05-08 cs.AI 61%

Contestable AI needs Computational Argumentation

可争议的AI需要计算论辩

Francesco Leofante, Hamed Ayoobi, Adam Dejl, Gabriel Freedman, Deniz Gorur, Junqi Jiang, Guilherme Paulino-Passos, Antonio Rago, Anna Rapberger, Fabrizio Russo, Xiang Yin, Dekai Zhang, Francesca Toni

机构 * Computational Logic and Argumentation Group, Department of Computing, Imperial College London, UK（计算逻辑与论证组，计算系，伦敦帝国学院，英国）

专题命中规划推理：reasoning(abstract,journal_ref)；分类 cs.AI

AI总结本文探讨如何通过计算论辩实现可争议的AI，强调动态可解释性和决策过程的重要性，以支持机器与人类或机器间的互动和争议解决。

Comments Accepted at KR 2024

Journal ref Proceedings of the International Conference on Principles of Knowledge Representation and Reasoning, 21, 888-896. 2024

1. 规划推理 11120 篇

Interaction-aware Multi-agent Tracking and Probabilistic Behavior Prediction via Adversarial Learning

Hindsight policy gradients

Provably Efficient Maximum Entropy Exploration

Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control

Mammalian Value Systems

Human-Like Autonomous Car-Following Model with Deep Reinforcement Learning

Automated Algorithm Selection: Survey and Perspectives

Combined Reinforcement Learning via Abstract Representations

Relational inductive biases, deep learning, and graph networks

Interactive Agent Modeling by Learning to Probe

Deep RTS: A Game Environment for Deep Reinforcement Learning in Real-Time Strategy Games

Neural Networks for Predicting Algorithm Runtime Distributions

On Learning Intrinsic Rewards for Policy Gradient Methods

Deep Reinforcement Learning for General Video Game AI

A Lyapunov-based Approach to Safe Reinforcement Learning

Multi-Advisor Reinforcement Learning

Self-Correcting Models for Model-Based Reinforcement Learning

Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving

Model-Free Imitation Learning with Policy Optimization

Model-Based Bayesian Exploration

Learning STRIPS Operators from Noisy and Incomplete Observations

Variance-Based Rewards for Approximate Bayesian Reinforcement Learning

A Bayesian Model for Plan Recognition in RTS Games applied to StarCraft

Unsupervised Learning in a Framework of Information Compression by Multiple Alignment, Unification and Search

Fine-tuning LLMs for Tourist Trajectory Prediction using Field Experiment Data

i-EXAM: Instructable and Explainable Attack Connectivity Graph Modeler

LaGO: Latent Action Guidance for Online Reinforcement Learning

PEACE: A Planner-Executor Agent with Constraint Enforcement for UAVs

Learning Lifted Action Models from Unsupervised Visual Traces

Contestable AI needs Computational Argumentation